Merge pull request #1454 from dbetebenner/master

Updating createSuperCohortData

.Rbuildignore

@@ -1,8 +1,8 @@
 ^docs$
-^_pkgdown\.yml$
 ^README\.md$
 ^LICENSE.md
 ^\.appveyor\.yml$
 ^vignettes/releases$
 ^\.github$
-^CITATION\.cff
+^CITATION\.cff$
+^_pkgdown\.yml$

CITATION.cff

@@ -11,7 +11,7 @@ authors:
 - family-names: "Shang"
   given-names: "Yi"
 title: "SGP: Student Growth Percentiles & Percentile Growth Trajectories"
-version: 2.2-0.3
+version: 2.2-0.4
 doi: 10.5281/zenodo.13921157
-date-released: 2024-10-10
+date-released: 2024-10-23
 url: "https://sgp.io"

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: SGP
 Type: Package
 Title: Student Growth Percentiles & Percentile Growth Trajectories
-Version: 2.2-0.3
-Date: 2024-10-10
+Version: 2.2-0.4
+Date: 2024-10-23
 Authors@R: c(person(given=c("Damian", "W."), family="Betebenner", email="[email protected]", role=c("aut", "cre"), comment=c(ORCID = "0000-0003-0476-5599")),
 		person(given=c("Adam", "R."), family="Van Iwaarden", email="[email protected]", role="aut"),
 		person(given="Ben", family="Domingue", email="[email protected]", role="aut"),

NAMESPACE

@@ -8,6 +8,7 @@ export(capwords)
 export(combineSGP)
 export(courseProgressionSGP)
 export(createKnotsBoundaries)
+export(createSuperCohortData)
 export(getStateAbbreviation)
 export(gofPrint)
 export(gofSGP)

R/createSuperCohortData.R

@@ -6,6 +6,8 @@ function(
         indicate_cohort=FALSE
 ) {
 
+  YEAR <- CONTENT_AREA <- GRADE <- YEAR_NEW <- COHORT <- ID <- NULL
+
   ### Parameters
   data.years <- sort(unique(base_data$YEAR))
   tmp.cohort.list <- list()
@@ -34,7 +36,7 @@ function(
 
       tmp.dt <- rbindlist(tmp.list)
       setkey(tmp.dt, YEAR, GRADE, ID)
-      tmp.dt <- tmp.dt[unique(tmp.dt[,.(YEAR, GRADE, ID)]), mult="last"] ### Remove duplicates created by collapsing data into YEAR_NEW taking LAST (most recent) case
+      tmp.dt <- tmp.dt[unique(tmp.dt[, .(YEAR, GRADE, ID)]), mult="last"] ### Remove duplicates created by collapsing data into YEAR_NEW taking LAST (most recent) case
     }
     tmp.cohort.list[[paste(sgp.config.iter[['sgp.content.areas']][1], paste(sgp.config.iter[['sgp.grade.sequences']], collapse=""), sep="_")]] <- tmp.dt
   }

R/zzz.R

@@ -1,12 +1,14 @@
 `.onLoad` <-
 function(libname, pkgname) {
-	setDTthreads(1)
+	available_threads <- data.table::getDTthreads()
+	data.table::setDTthreads(1)
+	utils::globalVariables(c("."))
 }
 
 
 `.onAttach` <-
 function(libname, pkgname) {
 	if (interactive()) {
-		packageStartupMessage(magenta$bold('SGP',paste(paste0(unlist(strsplit(as.character(packageVersion("SGP")), "[.]")), c(".", "-", ".", "")), collapse=""),' (10-10-2024). For help: >help("SGP") or visit sgp.io'))
+		packageStartupMessage(magenta$bold('SGP',paste(paste0(unlist(strsplit(as.character(packageVersion("SGP")), "[.]")), c(".", "-", ".", "")), collapse=""),' (10-23-2024). For help: >help("SGP") or visit sgp.io'))
 	}
 }

inst/CITATION

@@ -9,12 +9,12 @@ bibentry(
                     person(given = c("Yi"), family = "Shang")
                    ),
     year         = "2024",
-    note         = "R package version 2.2-0.1",
+    note         = "R package version 2.2-0.4",
     url          = "https://sgp.io",
     textVersion  = paste(
                     "Damian W. Betebenner, Adam R. Van Iwaarden, Benjamin Domingue and Yi Shang (2024).",
                     "SGP: Student Growth Percentiles & Percentile Growth Trajectories.",
-                    "(R package version 2.2-0.1)",
+                    "(R package version 2.2-0.4)",
                     "URL: https://sgp.io"
                   )
 )

man/SGP-package.Rd

@@ -19,8 +19,8 @@ growth projections to be calculated across assessment transitions by equating th
 \tabular{ll}{
 Package: \tab SGP\cr
 Type: \tab Package\cr
-Version: \tab 2.2-0.3\cr
-Date: \tab 2024-10-10\cr
+Version: \tab 2.2-0.4\cr
+Date: \tab 2024-10-23\cr
 License: \tab GPL-3\cr
 LazyLoad: \tab yes\cr
 }

man/createSuperCohortData.Rd

@@ -0,0 +1,103 @@
+\name{createSuperCohortData}
+\alias{createSuperCohortData}
+\title{Function to create longitudinal data set merging together individual years into a super-cohort of data.}
+\description{
+The function createSuperCohortData creates a longitudinal data set from another longitudinal data set in which individual years 
+are merged together in order to create a multi-year, super-cohort of longitudinal data. See examples below.
+}
+
+\usage{
+createSuperCohortData(
+		base_data,
+		sgp.config,
+		supercohort_base_years,
+		indicate_cohort=FALSE)
+}
+
+\arguments{
+  \item{base_data}{Longitudinal data from which to create the super-cohort. Longitudinal data is long formatted data where each row represents a unique student by grade by year by content area record. For SGP and sgpFlow analyses, data should, at a minimum provide the variables: 'VALID_CASE', 'CONTENT_AREA', 'YEAR', 'GRADE', 'SCALE_SCORE'. 
+  }
+  \item{sgp.config}{Configurations that detail the super-cohorts of student assessment records to be produced.  
+  }
+  \item{supercohort_base_years}{Subset of years in the supplied \code{base_data} to use for super-cohort construction.
+  }
+  \item{indicate_cohort}{Boolean variable (defaults to FALSE) indicating whether to include a variable in the super-cohort data set indicating from which cohort the data record emanates.
+  }
+}
+
+\value{Returns a data.table consisting of the multi-year, super-cohort data.
+}
+
+\author{Damian W. Betebenner \email{dbetebenner@nciea.org}}
+
+\examples{
+\dontrun{
+
+### super-cohort configurations
+MATHEMATICS.config <- list(
+	list(
+		sgp.content.areas=rep("MATHEMATICS", 2),
+		sgp.panel.years=c("2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("3", "4"),
+		sgp.grade.sequences.lags=1),
+	list(
+		sgp.content.areas=rep("MATHEMATICS", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("3", "4", "5"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("MATHEMATICS", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("4", "5", "6"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("MATHEMATICS", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("5", "6", "7"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("MATHEMATICS", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("6", "7", "8"),
+		sgp.grade.sequences.lags=c(1,1))
+)
+
+READING.config <- list(
+	list(
+		sgp.content.areas=rep("READING", 2),
+		sgp.panel.years=c("2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("3", "4"),
+		sgp.grade.sequences.lags=1),
+	list(
+		sgp.content.areas=rep("READING", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("3", "4", "5"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("READING", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("4", "5", "6"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("READING", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("5", "6", "7"),
+		sgp.grade.sequences.lags=c(1,1)),
+	list(
+		sgp.content.areas=rep("READING", 3),
+		sgp.panel.years=c("2021_2022", "2022_2023", "2023_2024"),
+		sgp.grade.sequences=c("6", "7", "8"),
+		sgp.grade.sequences.lags=c(1,1))
+)
+
+super_cohort_config <- c(MATHEMATICS.config, READING.config)
+
+super_cohort_data <- createSuperCohortData(
+					base_data=SGPdata::sgpData_LONG,
+					sgp.config=super_cohort_config)
+
+
+}  
+}
+
+\keyword{documentation}